Boosting a kNN Classifier by improving Feature Extraction for Authorship Identification of Source Code.
Yves BestgenPublished in: FIRE (Working Notes) (2020)
Keyphrases
- source code
- knn classifier
- k nearest neighbor
- knn
- feature extraction
- open source
- authorship attribution
- software systems
- nearest neighbor
- feature selection
- software maintenance
- open source software
- software projects
- input vector
- static analysis
- feature vectors
- high level
- learning algorithm
- software evolution
- plagiarism detection
- support vector machine
- version control
- text files
- source files
- free software
- program understanding
- support vector machine svm
- software repositories
- feature space
- support vector
- face recognition
- legacy software
- source code metrics
- neural network
- code examples
- legacy systems
- machine learning